JP6841254B2 - Image processing equipment and computer programs - Google Patents

Description

The present specification relates to image processing for image data generated by reading a printed matter using an image sensor, and more particularly to image processing for identifying character pixels in an image.

The image processing apparatus disclosed in Patent Document 1 executes edge determination for determining whether or not each pixel is an edge, and halftone dot determination for determining whether or not each pixel is a halftone dot. The image processing device identifies pixels that are edges and are not halftone dots as pixels that indicate characters.

Japanese Unexamined Patent Publication No. 6-164928 Japanese Unexamined Patent Publication No. 2004-104610

In the image data generated by reading the printed matter using the image sensor, halftone dots included in the printed matter appear in the image indicated by the image data. Pixels constituting such halftone dots are likely to be erroneously specified as character pixels when specifying character pixels in an image.

In this way, even for an image containing halftone dots, for example, there is a technique that can accurately identify character pixels by suppressing erroneous identification of character pixels in an area without characters due to halftone dots. I was asked.

The present specification discloses a technique capable of accurately identifying character pixels in a target image even if the image includes halftone dots.

The techniques disclosed in the present specification have been made to solve at least a part of the above-mentioned problems, and can be realized as the following application examples.

[Application Example 1] The image processing apparatus, which is an image acquisition unit that acquires target image data indicating a target image, and the target image data is generated by reading a printed matter using an image sensor. An image acquisition unit and a character identification unit that identifies a character pixel indicating a character from a plurality of pixels in the target image are provided, and the character identification unit uses the target image data in the target image. A plurality of first candidate pixels determined to be the edge pixels by determining for each pixel whether or not each of the plurality of pixels of the above is an edge pixel constituting an edge in the target image. Is determined, and using the target image data, histogram data showing the distribution of a plurality of pixels in the block is generated for each of the plurality of blocks arranged on the target image, and the histogram data is generated. By using each block to determine whether or not each of the plurality of blocks is a character block indicating a character, a plurality of second candidates in the block determined to be the character block are used. Pixels are determined, and among the plurality of pixels in the target image, the pixel determined to be the first candidate pixel and the second candidate pixel is defined as the character pixel. An image processing device to identify.

According to the above configuration, a plurality of first character candidate pixels are determined by the determination for each pixel, and a plurality of second character candidate pixels are determined by the determination for each block using the histogram data. Then, the pixel determined to be the first character candidate pixel and determined to be the second character candidate pixel is specified as the character pixel. As a result, for example, even if the pixel constituting the halftone dot is erroneously determined to be the first character candidate pixel by the determination for each pixel, the pixel constituting the halftone dot is the second pixel by the determination for each block. If it is not determined to be a character candidate pixel of, the pixel constituting the halftone dot is not erroneously specified as a character pixel. By using the histogram data for the determination for each block, the second character candidate pixel can be determined without requiring complicated processing for specifying the character candidate pixel. Therefore, for example, even in an image including halftone dots, character pixels in the target image can be specified with high accuracy.

The techniques disclosed in the present specification can be realized in various forms, for example, a multifunction device, a scanner, a printer, an image processing method, a function of these devices, or a computer for realizing the above method. It can be realized in the form of a program, a recording medium on which the computer program is recorded, or the like.

It is a block diagram which shows the structure of the multifunction device 200 which is an example of an image processing apparatus. It is a flowchart of image processing. FIG. 1 is a first diagram showing an example of an image used in image processing. It is a figure which shows an example of the image used in the character identification processing. It is a flowchart of the 1st binary image data generation processing. It is a flowchart of edge enhancement processing. It is explanatory drawing of the smoothed R component image data and edge-enhanced R component image data. It is a figure which shows an example of the tone curve for level correction processing. It is a flowchart of the 2nd binary image data generation processing. It is explanatory drawing of the minimum component value and the maximum component value of scan data. FIG. 2 is a second diagram showing an example of an image used for image processing. It is a flowchart of a block determination process. It is explanatory drawing of a plurality of blocks BL arranged on a scan image SI. It is a figure which shows an example of the histogram shown by the histogram data. It is a figure which shows an example of the judgment for each block BL. It is a figure which shows an example of setting of the pixel value in a block determination data. It is a figure explaining the effect of an Example.

A. Example:
A-1: Configuration of the multifunction device 200 An embodiment will be described based on an embodiment. FIG. 1 is a block diagram showing a configuration of a multifunction device 200, which is an example of an image processing device. The multifunction device 200 includes a CPU 210 which is a processor for controlling an image processing device, a volatile storage device 220 such as a DRAM, a non-volatile storage device 230 such as a flash memory and a hard disk drive, and a display unit 240 such as a liquid crystal display. An operation unit 250 including a touch panel and buttons superimposed on a liquid crystal display, an interface (communication IF) 270 for communicating with an external device such as a user's terminal device 100, a print execution unit 280, and a reading execution unit 290. , Is equipped.

The scanning execution unit 290 generates scan data by optically scanning the document using the one-dimensional image sensor under the control of the CPU 210. According to the control of the CPU 210, the print execution unit 280 uses a plurality of types of toners, specifically, cyan (C), magenta (M), yellow (Y), and black (K) toners as coloring materials. The image is printed on a printing medium such as paper by the laser method. Specifically, the print execution unit 280 exposes the photosensitive drum to form an electrostatic latent image, and attaches toner to the electrostatic latent image to form a toner image. The print execution unit 280 transfers the toner image formed on the photosensitive drum to the paper. In the modified example, the print execution unit 280 may be an inkjet type print execution unit that ejects ink as a coloring material to form an image on paper.

The volatile storage device 220 provides a buffer area for temporarily storing various intermediate data generated when the CPU 210 performs processing. The computer program PG is stored in the non-volatile storage device 230. The computer program PG is a control program that allows the CPU 210 to control the multifunction device 200. In this embodiment, the computer program PG is provided in a form that is pre-stored in the non-volatile storage device 230 at the time of manufacturing the multifunction device 200. Instead, the computer program PG may be provided in a form downloaded from a server, or may be provided in a form stored in a DVD-ROM or the like. The CPU 210 can execute image processing described later by executing the computer program PG.

A-2: Image processing FIG. 2 is a flowchart of image processing. This image processing is executed, for example, when the user places the document on the platen of the scanning execution unit 290 and inputs a copy execution instruction. In this image processing, scan data generated by scanning a document using a scanning execution unit 290 is acquired, and the scan data is used to generate print data indicating the document, thereby producing a so-called copy of the document. It is a process to be realized.

In S10, the CPU 210 generates scan data as target image data by reading the document placed on the platen by the user using the scanning execution unit 290. The manuscript is, for example, a printed matter in which an image is printed by a multifunction device 200 or a printer (not shown). The generated scan data is stored in the buffer area of the volatile storage device 220 (FIG. 1). The scan data includes the values of a plurality of pixels, and each of the values of the plurality of pixels represents the color of the pixel as an RGB color value (also referred to as an RGB value). That is, the scan data is RGB image data. The RGB value of one pixel includes, for example, the values of three color components (hereinafter, also referred to as R value, G value, and B value) of red (R), green (G), and blue (B). I'm out. In this embodiment, the number of gradations of each component value is 256 gradations.

The scan data, which is RGB image data, includes three component image data (R component image data, G component image data, B component image data) corresponding to the three color components constituting the RGB color system. Can be said. Each component image data is image data in which the value of one type of color component is used as the pixel value.

In S15, the CPU 210 executes an enlargement process for enlarging the scan image indicated by the scan data at an enlargement ratio Lr on the scan data to generate the enlarged scan data. The enlargement ratio Lr is input by the user, for example, together with a copy execution instruction. The enlargement ratio Lr is, for example, a value in the range of 0.1 to 6 (10% to 600%), and the enlargement processing at an enlargement ratio Lr of less than 1 is a process for reducing the size of the scanned image. The enlargement process at a larger enlargement ratio Lr is a process for increasing the size of the scanned image. Specifically, the size of the scanned image is defined by the number of pixels in the vertical and horizontal directions. The scan data before the enlargement processing is also referred to as the original image data, and the scan data after the enlargement processing is also referred to as the target image data. In the following, when simply referred to as scan data, it means scan data that has been enlarged.

FIG. 3 is a first diagram showing an example of an image used in image processing. FIG. 3A shows an example of the scanned image SI represented by the scan data. The scanned image SI includes a plurality of pixels. The plurality of pixels are arranged in a matrix along a first direction D1 and a second direction D2 orthogonal to the first direction D1.

The scanned image SI of FIG. 3A shows a white background Bg1 indicating the background color of the paper of the original, objects Ob1 to Ob3 different from the three characters, four characters Ob4 to Ob7, and four characters. The background Bg2 of the characters Ob4 to Ob7 and the like are included. Objects that are different from text are, for example, photographs. The background Bg2 is a uniform image having a color different from white.

In S20, the CPU 210 executes character identification processing on the scan data. The character identification process is a process for identifying character pixels by classifying a plurality of pixels in the scanned image SI into a plurality of character pixels indicating characters and a plurality of non-character pixels not indicating characters. Is.

By the character identification process, for example, binary image data (also referred to as character identification data) in which the value of the character pixel is set to "1" and the value of the non-character pixel is set to "0" is generated. FIG. 3B shows an example of the character identification image TI indicated by the character identification data. In this character identification image TI, a plurality of pixels constituting the edges of the four characters Ob4 to Ob7 in the scanned image SI are specified as character pixels Tp4 to Tp7. For relatively large characters, the pixels constituting the edges of the characters are specified as character pixels, and for relatively small characters, the entire pixels constituting the characters are specified as character pixels. The details of the character identification process will be described later.

In S30, the CPU 210 executes a halftone dot smoothing process on the scan data to generate smoothed image data indicating the smoothed image. Specifically, the CPU 210 executes a smoothing process using a smoothing filter such as a Gaussian filter on each of the values of a plurality of non-character pixels included in the scan data, and the smoothing process has been completed. Calculate the values of a plurality of non-character pixels. The non-character pixel to be smoothed is specified by referring to the character identification data generated by the classification process of S20. The CPU 210 generates smoothed image data including the values of the plurality of character pixels included in the scan data and the values of the plurality of non-character pixels that have been smoothed.

FIG. 3C shows a smoothed image GI represented by the smoothed image data. The smoothed image GI contains 1 g of a white background Bg, objects Ob1 to Ob7 in the scanned image SI, objects Ob1g to Ob7g in which the background Bg2 is smoothed, and 2 g of a background Bg. Of these objects Ob1g to Ob7g and background Bg2g, parts other than the characters Ob4g to Ob7g (also referred to as non-character parts) are smoothed as compared with the scanned image SI.

In S40, the CPU 210 executes character sharpening processing on the smoothed image data to generate processed image data. Specifically, the CPU 210 executes a sharpening process such as an unsharp mask process or a process of applying a sharpening filter on each of the values of a plurality of character pixels included in the smoothed image data. Calculate the values of a plurality of character pixels that have been sharpened. The character pixel to be sharpened is specified by referring to the character identification data generated by the classification process of S20. Then, the CPU 210 includes the values of the plurality of non-character pixels included in the smoothed image data (values of the plurality of non-character pixels that have been smoothed) and the values of the plurality of character pixels that have been sharpened. Generates processed image data including ,. Since the values of the plurality of character pixels included in the smoothed image data are not subject to the smoothing process, they are the same as the values of the plurality of character pixels included in the scan data. Therefore, it can be said that the character sharpening process of this step is executed for the values of a plurality of character pixels included in the scan data.

FIG. 3D shows the processed image FI represented by the processed image data. The processed image FI includes a white background Bg1f, objects Ob1 to Ob7 in the scanned image SI, objects Ob1f to Ob7f corresponding to the background Bg2, and a background Bg2f. Of these objects Ob1f to Ob7f and the background Bg2f, the edges of the characters Ob4f to Ob7f are sharpened as compared with the characters Ob4 to Ob7 in the scanned image SI and the characters Ob4g to Ob7g in the smoothed image GI. There is. Further, the edges of the objects Ob1f to Ob3f and the background Bg2f other than the characters are not sharpened.

As can be seen from the above description, the objects Ob1f to Ob7f and the background Bg2f in the processed image FI include sharpened characters and smoothed non-characters.

In S50, the CPU 210 executes a print data generation process for generating print data using the processed image data. Specifically, a color conversion process is executed on the processed image data which is RGB image data, and a color having color components (C, M, Y, K components) corresponding to the color material used for printing is performed. CMYK image data indicating the color for each pixel is generated by the CMYK value which is a value. The color conversion process is executed with reference to, for example, a known look-up table. Halftone processing is executed on the CMYK value image data, and dot data indicating a dot formation state is generated for each color material used for printing and for each pixel. The dot formation state can be, for example, two types of states with or without dots, and four types of states of large dots, medium dots, small dots, and no dots. The halftone processing is executed according to, for example, a dither method or an error diffusion method. The dot data are rearranged in the order in which they are used at the time of printing, and print data is generated by adding a print command to the dot data.

In S60, the CPU 210 executes the print process and ends the image process. Specifically, the CPU 210 supplies print data to the print execution unit 280, and causes the print execution unit 280 to print the processed image.

According to the image processing described above, the first image processing (specifically, the edge sharpening process) is executed for the values of the plurality of specified character pixels in the scan data (S40). A second image process (specifically, halftone dot smoothing process) different from the first image process is executed for the values of the plurality of non-character pixels (S30), and the processed image data is generated. To. As a result, different image processing is executed for the value of the character pixel and the value of the pixel different from the character pixel, so that appropriate image processing for the scan data can be realized. In the modified example, the character sharpening process of S40 may be executed first, and then the halftone dot smoothing process of S30 may be executed.

More specifically, processed image data including the values of the plurality of character pixels that have been sharpened and the values of the plurality of non-character pixels that have been smoothed is generated (S30, S40). .. As a result, it is possible to generate processed image data showing the processed image FI that looks good.

For example, as shown in the processed image FI of FIG. 3D, in the processed image data, the sharpening-processed value is used as the value of the character pixel. As a result, the characters of the processed image FI look sharp, so that the appearance of the processed image FI to be printed can be improved, for example.

Further, in the processed image data, the smoothed values are used as the values of the background Bg2f in the processed image FI and the non-character pixels constituting an object different from the characters such as a photograph. As a result, for example, it is possible to suppress the appearance of halftone dots that cause moire in a portion different from the characters of the processed image FI, so that it is possible to prevent problems such as moire from occurring in the printed processed image FI. it can. As a result, the appearance of the processed image FI to be printed can be improved. In addition, since the edges in the photograph are suppressed from being excessively emphasized, the appearance of the image FI can be improved.

For example, the original used to generate the scan data is a printed matter on which an image is printed. Therefore, for example, a uniform portion such as a background Bg2 having a color different from white in a document forms halftone dots when viewed at the dot level forming an image. The halftone dots include a plurality of dots and a portion where the dots are not arranged (a portion indicating the ground color of the document). For this reason, halftone dots are shown in the region showing the background Bg2 in the scanned image SI when viewed at the pixel level. The dots in the halftone dots are arranged with periodicity due to the influence of the dither matrix used when printing the original. For this reason, when printing is performed using scan data, the periodic components of halftone dot dots existing in the original image (scan image SI) before halftone processing and the dots of halftone dots that make up the printed image Moire is likely to appear due to interference with the periodic component. In the processed image FI of this embodiment, the smoothing process reduces the periodic component of dots in a portion different from the edge in the original image (scanned image SI). As a result, when the processed image FI is printed using the processed image data, for example, it is possible to suppress the occurrence of moire in the printed processed image FI.

In particular, in the above image processing, print data is generated using the processed image data (S50). Therefore, for example, appropriate print data capable of suppressing moire that tends to occur in the processed image FI to be printed is generated. can do.

A-3: Character identification process The character identification process of S20 in FIG. 2 will be described. In S22, the CPU 210 uses the scan data to execute the first binary image data generation process to generate the first binary image data. The first binary image data is binary data indicating edge pixels and non-edge pixels. Here, the edge pixel represented by the first binary image data is also referred to as a first edge pixel, and the non-edge pixel represented by the first binary image data is also referred to as a first non-edge pixel. Details of the first binary image data generation process will be described later.

In S24, the CPU 210 uses the scan data to execute the second binary image data generation process to generate the second binary image data. The second binary image data, like the first binary image data, is binary data indicating edge pixels and non-edge pixels. The second binary image data is generated by a process different from that of the first binary image data, and is different from the first binary image data. Here, the edge pixel represented by the second binary image data is also referred to as a second edge pixel, and the non-edge pixel represented by the second binary image data is also referred to as a second non-edge pixel. Details of the second binary image data generation process will be described later.

In S26, the CPU 210 executes a logical sum composition process for synthesizing the first binary image data generated in S22 and the second binary image data generated in S24, and finally. Binary image data (also referred to as edge specific data) indicating edge pixels and non-edge pixels specified in is generated. Specifically, the CPU 210 generates binary image data as edge specific data by ORing each pixel of the first binary image data and the second binary image data. In other words, the CPU 210 has a plurality of first edge pixels identified by the first binary image data and a plurality of second edge pixels identified by the second binary image data. A pixel group that includes pixels and does not include pixels that are different from the first edge pixel and the second edge pixel is finally specified as a plurality of edge pixels. As a result, using the first binary image data and the second binary image data, it is possible to accurately determine whether or not the pixels in the target image are edge pixels. For example, the specific omission of edge pixels in the scanned image SI can be effectively reduced.

The edge pixel specified by the edge specific data is a pixel that is a candidate for a character pixel, and is also called a first character candidate pixel. For example, in the edge identification data, the value of the first character candidate pixel (edge pixel in this embodiment) is set to "1", and the value of the pixel that is not the first character candidate pixel (non-edge pixel in this embodiment). It is binary image data whose value is set to "0".

FIG. 4 is a diagram showing an example of an image used in the character identification process. FIG. 4A shows an example of the edge-specific image EI represented by the edge-specific data. The edge specific image EI includes a plurality of edge pixels constituting the edges Eg1 to Eg7 of the objects Ob1 to Ob7 in the scanned image SI, and a plurality of edges forming the edge Eg8 at the boundary between the background Bg1 and the background Bg2. The pixel is specified as the first character candidate pixel. As described above, the edge indicated by the first character candidate pixel includes the character edge. Further, the edge includes an edge such as a thin line contained in an object (for example, a photograph) different from the character.

In S28, the CPU 210 executes a block determination process on the scan data to show a binary image showing a second character candidate pixel that is a candidate for a character pixel and a pixel that is not a second character candidate pixel. Generate data (also called block judgment data). The block determination process is a process of determining for each block whether or not each of the plurality of blocks arranged in the scanned image SI is a character block indicating a character by using the scan data. One block is a rectangular area containing N pixels (N is an integer of 2 or more). Although the details will be described later, it is determined whether or not the plurality of pixels in the scanned image SI are the second character candidate pixels based on the determination result for each block. The block determination data is binary image data in which the value of the second character candidate pixel is "1" and the value of the pixel other than the second character candidate pixel is "0".

FIG. 4B shows an example of the block determination image BI shown by the block determination data. In this block determination image BI, second character candidate pixels Bk4 to Bk7g1 indicating an area in which characters Ob4 to Ob7 are arranged in the scan image SI are specified. As described above, the area indicated by the second character candidate pixel includes the character area including the character and does not include the area including the object (for example, a photograph) different from the character.

In S29, the CPU 210 executes a logical product composition process for synthesizing the edge identification data generated in S26 and the block determination data generated in S28 to indicate the character pixels and the non-character pixels. Generate the character-specific data (see FIG. 3B). Specifically, the CPU 210 generates binary image data as character identification data by taking the logical product of each pixel of the edge identification data and the block determination data. In other words, the CPU 210 is determined to be the first character candidate pixel in S22 to S26 and the second character candidate pixel in S28 among the plurality of pixels in the scanned image SI. Pixel is specified as a character pixel. Of the plurality of pixels in the scanned image SI, the CPU 210 uses pixels that are determined not to be the first character candidate pixels and pixels that are determined not to be the second character candidate pixels as non-character pixels. Identify. When the character identification data is generated, the character identification process is terminated.

A-4: First binary image data generation process The first binary image data generation process in S22 of FIG. 2 will be described. FIG. 5 is a flowchart of the first binary image data generation process. In S100, the CPU 210 executes a smoothing process on each of the three component image data included in the scan data, that is, the R component image data, the G component image data, and the B component image data. As a result, three smoothed component image data, that is, smoothed R component image data, smoothed G component image data, and smoothed B component image data are generated.

The smoothing process is a process for smoothing a component image indicated by the component image data to be processed. The smoothing process of this embodiment is a process of applying a predetermined smoothing filter to the value of each pixel of the component image data to be processed to calculate the value of each pixel that has been smoothed. As the smoothing filter, for example, a Gaussian filter having a size of 7 pixels in the vertical direction and 7 pixels in the horizontal direction is used.

In S110, edge enhancement processing is executed for each of the three smoothed component image data, and the three edge-enhanced component image data, that is, the edge-enhanced R component image data and the edge. The emphasized G component image data and the edge emphasized B component image data are generated.

FIG. 6 is a flowchart of edge enhancement processing. Here, it will be described that the smoothed R component image data is the processing target. The same processing is performed on the smoothed G component image data and the smoothed B component image data.

In S200, the CPU 210 prepares canvas data for generating edge-enhanced R component image data in a memory (specifically, a buffer area of the volatile storage device 220). The canvas (initial image) indicated by the canvas data is an image having the same size as the scanned image SI, that is, an image having the same number of pixels. The value of each pixel of the canvas data is a predetermined initial value (for example, 0).

In S205, the CPU 210 selects one pixel of interest from a plurality of pixels in the smoothed R component image indicated by the smoothed R component image data.

In S210, the CPU 210 calculates the mask value MV corresponding to the pixel of interest. The mask value MV smoothes the value TV of the pixel of interest by using the value TV of the pixel of interest and the value of a predetermined number of peripheral pixels including four pixels vertically and horizontally adjacent to the pixel of interest. Calculated by processing. For this reason, the mask value MV is also referred to as a smooth value. Specifically, the average value of the values of 100 pixels within the rectangular range of 10 pixels in the vertical direction and 10 pixels in the horizontal direction centered on the pixel of interest is calculated as the mask value MV corresponding to the pixel of interest.

In S220, the CPU 210 calculates the difference ΔV between the value TV of the pixel of interest and the mask value MV corresponding to the pixel of interest (ΔV = (TV-MV)).

In S230, the CPU 210 determines whether or not the difference ΔV is equal to or greater than the reference value. Specifically, it is determined whether or not the difference ΔV is equal to or greater than a predetermined threshold value TH. The threshold value TH is, for example, a value of about 20 to 30 when the component value is a value of 256 gradations in the range of 0 to 255.

When the difference ΔV is equal to or greater than the reference value (S230: YES), in S240, the CPU 210 processes the sum (TV + ΔV) of the value TV of the pixel of interest and the difference ΔV corresponding to the pixel of interest. Calculate as. If the difference ΔV is less than the reference (S230: NO), the CPU 210 skips S240.

In S245, the CPU 210 records the value of the pixel of interest in the canvas data prepared in S200. When S240 is executed, the sum of the value TV of the pixel of interest calculated in S240 and the difference ΔV corresponding to the pixel of interest is recorded in the canvas data as a processed value. When S240 is skipped, the value of the pixel of interest in the smoothed R component image data is recorded in the canvas data as it is.

In S250, the CPU 210 determines whether or not all the pixels in the R component image have been processed as the pixels of interest. If there are unprocessed pixels (S250: NO), the CPU 210 returns to S205 and selects the unprocessed pixels as the pixels of interest. When all the pixels have been processed (S250: YES), the CPU 210 ends the edge enhancement process. At this point, edge-enhanced R component image data is generated.

FIG. 7 is an explanatory diagram of the smoothed R component image data and the edge-enhanced R component image data. FIG. 7A shows a graph conceptually showing the R component image data of S100 of FIG. 5 before the smoothing process. 7 (B) and 7 (C) show graphs conceptually showing the smoothed R component image data and the edge-enhanced R component image data, respectively. In each graph, the left part conceptually shows a halftone dot area indicating a halftone dot, and the right part conceptually shows an edge area indicating an edge of an object such as a character. The vertical axis of each graph indicates the value of the R component, and the horizontal axis indicates the position in a predetermined direction (for example, the first direction D1 in FIG. 3).

The R component image data before the smoothing process includes, for example, a plurality of halftone dots C1 to C3 corresponding to a plurality of halftone dots and a plurality of gaps between the halftone dots in the halftone dot region. A plurality of mountain portions P1 and P2 appear (FIG. 7 (A)). If the difference in the value of the R component between the valleys C1 to C3 and the plurality of peaks P1 and P2 remains large, the R is found in the binarization process of S150 described later. Due to the difference in the value of the component, the edge pixel indicating the halftone dot is easily identified. The halftone dot region includes halftone dots from a pixel-level viewpoint (a micro viewpoint that can recognize halftone dots), but from an observer's viewpoint (a macro viewpoint that cannot recognize halftone dots). , A uniform area. Therefore, in this embodiment, the edge pixels caused by the halftone dots should not be specified in the halftone dot region. This is because the halftone dot region is preferably smoothed in S30 of FIG. 2 and should not be sharpened in S40. If the edges of the halftone dots are sharpened, the periodicity of the halftone dots becomes conspicuous, so that moire becomes conspicuous when printing the image. For example, edge pixels should not be specified in a uniform part such as the background Bg2 in the scanned image SI or a part different from the edge of the object.

In the smoothed R component image data, due to the smoothing process, for example, in the halftone dot region, the difference between the R component values of the plurality of valley portions C1a to C3a and the plurality of peak portions P1a and P2a is increased. , It is sufficiently smaller than the R component image data before the smoothing process (FIG. 7 (B)).

Here, in the edge enhancement process of this embodiment, the larger the difference ΔV between the value TV of the pixel of interest and the mask value MV corresponding to the pixel of interest, the greater the effect of edge enhancement. Therefore, the effect of edge enhancement becomes small in a region where the difference in the values of the R components is relatively small and flat, such as the halftone dot region of FIG. 7B. Further, in the edge enhancement process of this embodiment, when the difference ΔV is less than the reference value, the edge enhancement is not performed and the pixel value of the smoothed R component image data is adopted as it is (FIG. 6). S230). As a result, in the edge-enhanced R component image data, for example, in the halftone dot region, a plurality of valley portions C1b to C3b and a plurality of mountain portions P1b, despite the edge enhancement processing being performed. The difference between the R component values of P2b and that of P2b is not larger than that of the smoothed R component image data (FIG. 7 (C)). That is, similarly to the smoothed R component image data, in the edge-enhanced R component image data, the values of the R components of the plurality of valleys C1b to C3b and the plurality of peaks P1b and P2b The difference is sufficiently smaller than the R component image data (FIG. 7 (A)) before the smoothing process (FIG. 7 (C)).

In the R component image data before the smoothing process, for example, in an edge region indicating an edge of an object such as a character, a variable portion E1 in which the value of the R component suddenly changes corresponding to the edge appears (FIG. 7 (FIG. 7). A)). In such a variable portion E1, the larger the change in the value, the easier it is to identify the edge pixel indicating the edge of the object due to the difference in the value of the R component in the binarization process of S150 described later.

In the smoothed R component image data, for example, in the edge region, the change in the value in the variable portion E1a is smaller (gradually) than the R component image data before the smoothing process due to the smoothing process. (Fig. 7 (B)).

However, since the change in the value in the variable portion E1a corresponding to the edge of the object such as a character is sufficiently larger than the change in the value in the halftone dot region, the edge enhancement process returns to the sudden change again. As a result, in the edge-enhanced R component image data, the change in the value of the R component of the variable portion E1b in the edge region is larger than that in the smoothed R component image data (FIG. 7 (FIG. 7). C)). Therefore, in the edge-enhanced R component image data, the change in the value in the variable portion E1b in the edge region is about the same as or abrupt as compared with the R component image data before the smoothing process. (Fig. 7 (C)).

As can be seen from the above description, in this embodiment, the smoothing process (S100) and the edge enhancement process (S110) are executed in this order for each component image data, so that the edges of the halftone dots are formed. It is possible to suppress the identification of the indicated edge pixel, and it is possible to promote the identification of the edge pixel indicating the edge of an object such as a character. As a result, a plurality of edge pixels in the scanned image SI can be appropriately specified.

When three enhanced component image data corresponding to the three color components of R, G, and B are generated, in 120 of FIG. 5, the three enhanced component image data are used. , Generates luminance image data. The luminance image data is data indicating the luminance of a plurality of pixels in the enhanced image indicated by the three enhanced component image data. Specifically, the CPU 210 calculates the brightness value Y of each pixel by using the R value, G value, and B value of each pixel acquired from the three enhanced component image data. The luminance value Y is, for example, a weighted average of the above three components, and can be specifically calculated using the formula Y = 0.299 × R + 0.587 × G + 0.114 × B. Luminance image data is single-component image data composed of one type of component value (value indicating brightness). The luminance component data includes a luminance value Y based on the corresponding pixel value (RGB value) of the scan data for each pixel. The luminance component data is an example of the first image data.

In S130, the CPU 210 executes an edge extraction process for extracting the edge in the luminance image indicated by the luminance image data on the generated luminance image data to generate the edge extraction data. Specifically, the CPU 210 applies a known edge extraction filter, for example, a Sobel filter, to the value of each pixel of the luminance image data to calculate the edge intensity of each pixel. The CPU 210 generates edge extraction data in which these edge intensities are set as the values of a plurality of pixels.

In S140, the CPU 210 executes level correction processing on the edge extraction data to generate the corrected edge extraction data. The level correction process is a correction process for expanding a specific range within a range of gradation values (range 0 to 255 in this embodiment) that the pixel value of the edge extraction data can take.

FIG. 8 is a diagram showing an example of a tone curve for level correction processing. Specifically, the CPU 210 applies the tone curve of FIG. 8 to each pixel of the edge extraction data. As a result, all the values above the threshold value Vb (for example, 245) are converted into the maximum value (255), and all the values below the threshold value Va (for example, 10) are converted into the minimum value (0). Then, the range larger than the threshold value Va and less than the threshold value Vb is expanded to the range of 0 to 255. In this way, before the binarization process of S150 described later, the range including the binarization threshold value (the range larger than the threshold value Va and less than the threshold value Vb in FIG. 8) is expanded, so that the binarization accuracy Can be improved.

In S150, the CPU 210 executes a binarization process on the corrected edge extraction data to generate binary image data. For example, in the edge image data, the CPU 210 classifies pixels having a pixel value (that is, edge strength) equal to or greater than a threshold value (for example, 128) as edge pixels, and non-pixels having a pixel value less than the threshold value. Classify as edge pixels. In the binary image data, as described above, the value of the edge pixel is set to "1", and the value of the non-edge pixel is set to "0".

According to the first binary image data generation process described above, as described with reference to FIG. 7, by executing the smoothing process for each of the plurality of component image data, the scanned image SI The characteristics of halftone dots appearing inside can be reduced. Further, as described with reference to FIG. 7, by performing edge enhancement processing on each of the plurality of smoothed component image data, the inside of the scanned image SI smoothed by the smoothing process is performed. Can properly emphasize the edges of. As a result, the edge pixels in the scanned image SI can be appropriately specified while suppressing the identification of the edge pixels caused by the halftone dots.

Further, since the luminance image data is used as the single component image data, it is possible to more appropriately identify a plurality of edge pixels in the scanned image SI. For example, halftone dots often have the primary colors C, M, and Y used for printing, but such a difference between a plurality of primary colors is relatively large in each component image data of R, G, and B. However, it is relatively small in the luminance image data. Therefore, by using the luminance image data, it is possible to appropriately suppress the identification of edge pixels caused by halftone dots. Further, for the sake of readability of characters, there is often a relatively large difference in brightness between the color of characters and the color of the background. Therefore, by using the luminance image data, it is possible to appropriately identify the edge pixels indicating the edges of the object such as characters.

Further, in the edge enhancement process of FIG. 6, the calculation of the mask value (also referred to as the smooth value) corresponding to the pixel of interest (S210) and the calculation of the difference ΔV between the value TV of the pixel of interest and the mask value corresponding to the pixel of interest (S210). The so-called unsharp mask processing including the calculation (S240) of the sum (TV + ΔV) of S220) and the value TV of the pixel of interest and the corresponding difference ΔV is executed. As a result, since the edge of the scanned image SI can be appropriately emphasized, it is possible to suppress the specification omission of the edge pixel to be specified. As a result, the edge pixels in the scanned image SI can be more appropriately identified.

Further, in the edge enhancement processing of FIG. 6, among the plurality of pixels in the scanned image SI, the pixels whose corresponding difference ΔV is equal to or more than the reference are subject to the unsharp mask processing, and the difference ΔV is less than the reference. Pixels that are are not subject to unsharp mask processing (S230, 240). As a result, as described with reference to FIG. 7, it is possible to further suppress the emphasis of the difference in values between the pixels due to the halftone dots of the scanned image SI, so that the edge pixels due to the halftone dots can be specified. It can be further suppressed. Then, the edges of objects such as characters can be appropriately emphasized. Therefore, the edge pixels in the scanned image SI can be more appropriately specified.

A-5: Second binary image data generation process The second binary image data generation process of S24 of FIG. 2 will be described. FIG. 9 is a flowchart of the second binary image data generation process. In S300, the CPU 210 uses the scan data to generate the minimum component data. Specifically, the CPU 210 acquires the minimum component value Vmin from each of the values (RGB values) of the plurality of pixels included in the scan data. The minimum component value Vmin is the minimum value among a plurality of component values (R value, G value, B value) included in the RGB value. The CPU 210 generates image data in which these minimum component values Vmin are the values of a plurality of pixels as the minimum component data. The minimum component data is image data indicating an image having the same size as the scanned image SI. Each of the values of the plurality of pixels included in the minimum component data is the minimum component value Vmin of the corresponding pixel value (RGB value) of the scan data.

FIG. 10 is an explanatory diagram of the minimum component value and the maximum component value of the scan data. 10 (A) to 10 (E) show a bar graph showing RGB values of cyan (C), magenta (M), yellow (Y), black (K), and white (W) as an example of RGB values. Is illustrated in. As shown in FIG. 10, the RGB values (R, G, B) of C, M, Y, K, and W are (0, 255, 255), (255, 0, 255) (255, 255, respectively). 0), (0, 0, 0), (255, 255, 255).

As described above, the luminance value Y of these RGB values can be calculated using, for example, the formula Y = 0.299 × R + 0.587 × G + 0.114 × B. The brightness of C, M, Y, K, and W (represented by a value of 0 to 255) is about 186, 113, 226, 0, 255, and each has a different value (FIG. 10). On the other hand, the minimum component values Vmin of C, M, Y, K, and W are 0, 0, 0, 0, 255 as shown in FIG. 10, and are the same values except for white (W). ..

FIG. 11 is a second diagram showing an example of an image used for image processing. FIG. 11A is an enlarged view of the halftone dot region described above in the scanned image SI. For example, in the example of FIG. 11A, the halftone dot region in the scanned image SI includes a plurality of M dot MDs and a plurality of Y dots YD. Here, for the sake of explanation, it is assumed that the image showing the M dot MD is a uniform image having the primary color of magenta, and the image showing the Y dot YD is a uniform image having the primary color of yellow.

FIG. 11B shows an example of the minimum component image MNI represented by the minimum component data. This minimum component image MNI corresponds to the scanned image SI of FIG. 11 (A). In the minimum component image MNI, the values of the pixels in the region MDb corresponding to the Y dot MD of the scanned image SI and the values of the pixels in the region YDb corresponding to the Y dot YD are the same as each other. As a comparative example, FIG. 11C shows a luminance image YI represented by luminance image data indicating the luminance of each pixel. This luminance image YI corresponds to the scanned image SI of FIG. 11 (A). In the luminance image YI, unlike the minimum component image MNI, the values of the pixels in the region MDd corresponding to the M dot MD of the scan image SI and the values of the pixels in the region YDd corresponding to the Y dot YD are different from each other. ..

As can be seen from the above description, in the minimum component image MNI, in the scanned image SI, the difference between the values of the plurality of pixels corresponding to the portions where the C, M, Y, and K dots are formed in the document is large. It is smaller than the luminance image YI. Then, in the minimum component image MNI, in the scanned image SI, the pixel value of the ground color region corresponding to the region indicating the ground color (white of the paper) in the document is the pixel value corresponding to the portion where the dots are formed. Will be larger than.

In S310, the CPU 210 executes a smoothing process for smoothing the minimum component image MNI indicated by the minimum component data on the generated minimum component data to generate the smoothed minimum component data. Specifically, the CPU 210 applies a predetermined smoothing filter to the value of each pixel of the minimum component data, and in this embodiment, a Gaussian filter of 5 pixels in the vertical direction and 5 pixels in the horizontal direction. Calculate the pixel value. The smoothed minimum component data includes the smoothed value generated by the above-described processing based on the corresponding pixel value (RGB value) of the scan data for each pixel. The smoothed minimum component data is an example of the second image data.

In S320, the CPU 210 executes an edge extraction process for extracting the edge in the smoothed minimum component image MNI indicated by the smoothed minimum component data with respect to the smoothed minimum component data. Generate edge extraction data. Specifically, the CPU 210 applies the same Sobel filter as the process of S130 in FIG. 5 to the value of each pixel of the smoothed minimum component data to calculate the edge strength. The CPU 210 generates edge extraction data in which these edge intensities are set as the values of a plurality of pixels.

In S330, the CPU 210 executes level correction processing on the edge extraction data to generate the corrected edge extraction data. The level correction process is the same as the process of S140 in FIG. In S340, the CPU 210 executes a binarization process similar to the process of S150 of FIG. 5 on the corrected edge extraction data to generate binary image data. In the binary image data, as described above, the value of the edge pixel is set to "1", and the value of the non-edge pixel is set to "0".

According to the second binary image data generation process described above, the edge extraction process is executed for the minimum component data, and the edge extraction data is generated (S320). Then, by executing the edge pixel identification process including the process of binarizing the edge extraction data (S340), a plurality of edge pixels of the scanned image SI are specified (S330, S340, S26 in FIG. 2). .. In the minimum component data, as described with reference to FIG. 11, since the difference in the values between the pixels can be suppressed in the halftone dot region, the edge pixels caused by the halftone dots are subsequently identified when the edge pixels are specified. Can be suppressed from being identified. Therefore, the edge pixels in the scanned image SI can be appropriately specified.

More specifically, there are five types of elements constituting the halftone dot region: dots C, M, Y, and K, and the background color (white) of the paper. In the minimum component data, it is possible to suppress the difference in value between the pixels indicating the four types of elements among these elements. As a result, when the minimum component data is used, it is possible to suppress the identification of edge pixels indicating the edges of halftone dots.

On the other hand, in many cases, one of the character color and the background color has a dark color and the other has a light color. For this reason, one of the characters and the background contains a relatively large amount of the background color (white) of the paper, and the other contains a relatively large amount of C, M, Y, and K dots. There are many. As shown in FIG. 10, in the minimum component data, between the pixel value of the portion indicating the dots of C, M, Y, and K and the pixel value of the portion indicating the ground color (white) of the paper, There is a big difference. Therefore, when the edge pixels are specified using the minimum component data, there is a high possibility that the edge pixels constituting the edges of the character can be appropriately specified. In particular, yellow (Y) has a lower concentration (higher brightness) than C, M, and K. For this reason, when there are yellow characters on the background of the background color (white) of the paper, even if the luminance image data is binarized, the edge pixels constituting the edges of the yellow characters are appropriately specified. It may not be possible. In this embodiment, even in such a case, the edge pixels constituting the edge of the yellow character can be appropriately specified. For this purpose, in addition to the identification of the edge pixel using the luminance image data, the edge pixel identification using the minimum component data is executed to identify the edge pixel such as a character that cannot be identified only by the luminance image data. obtain. As a result, the accuracy of identifying the edge pixels in the scanned image SI can be improved.

Further, a smoothing process is executed for the minimum component data before the edge extraction process (S310). As a result, the smoothing process can further suppress the difference in values between pixels in the halftone dot region in the minimum component image MNI. For example, in the halftone dot region in the scanned image SI, the portion indicating the dots is not necessarily C, M, Y due to the overlap of dots of C, M, Y, and K and the blurring during reading by the reading execution unit 290. , Does not have the primary color of K. Therefore, in the minimum component image MNI, the value between the plurality of pixels indicating the dots C, M, Y, and K is small, but not zero. The smoothing process can further reduce the difference in values between the pixels. As a result, it is possible to further suppress the identification of edge pixels caused by halftone dots. Further, in the second binary image data generation process as well, the level correction process (S330) is executed in the same manner as in the first binary image data generation process, so that the accuracy of specifying the edge pixels in the scanned image SI can be determined. Can be improved.

As described above, in the above embodiment, the edge pixels are finally specified by using two types of single component image data, that is, the luminance image data and the minimum component data (S22 to S22 in FIG. 2). S26). Since a plurality of edge pixels in the scan image SI are specified by using the two types of single component image data generated by using different processes in this way, the plurality of edge pixels in the scan image SI can be identified. Specific leakage can be suppressed. For example, when there is a yellow character on a white background, the difference in brightness between white and yellow is relatively small, so it is difficult to identify the edge pixels that make up the edge of the character using the brightness image data. Is. On the other hand, as can be seen from FIGS. 10 (C) and 10 (E), in the minimum component data, a large difference between white and yellow appears. Therefore, when there are yellow characters on a white background, the minimum component It is easy to identify the edge pixels that make up the edge of the character using the data. Further, for example, when there is a yellow character in the background of magenta, the difference between magenta and yellow does not appear in the minimum component data, so the edge pixels constituting the edge of the character are used using the minimum component data. Is difficult to identify. On the other hand, when there is a yellow character in the background of magenta, the difference in brightness between magenta and yellow is relatively large, so the edge pixels constituting the edge of the character are specified using the brightness image data. It's easy to do.

Further, since the single component image data used in addition to the luminance image data is the minimum component data, it is possible to suppress the identification of edge pixels caused by halftone dots in the scanned image SI as described above.

A-6: Block determination process The block determination process of S28 in FIG. 2 will be described. FIG. 12 is a flowchart of the block determination process. FIG. 13 is an explanatory diagram of a plurality of blocks BL arranged on the scanned image SI. As described above, in the block determination process, a plurality of block determination data indicating a second character candidate pixel that is a candidate for a character pixel and a pixel that is not a second character candidate pixel are arranged in the scan image SI. This is a process generated by determining for each block BL whether or not each of the block BLs of the above is a character block indicating a character.

In S400, the CPU 210 prepares canvas data for generating block determination data in a memory (specifically, a buffer area of the volatile storage device 220). The canvas (initial image) indicated by the canvas data is an image having the same size as the scanned image SI, that is, an image having the same number of pixels. The value of each pixel of the canvas data is a predetermined initial value (for example, 0).

In S405, the CPU 210 sets a block of interest in the scanned image SI. The first block of interest is the block BL (1) in the upper left of FIG. 13 in this embodiment. One block is a rectangular area containing N pixels (N is an integer of 2 or more). Here, in FIG. 13, a plurality of squares indicated by broken lines arranged in a matrix on the scanned image SI indicate a sub-block SB. One subblock SB is a rectangular area containing k pixels (k is an integer satisfying 1 ≦ k <N). In this embodiment, the sub-block SB is an area of vertical M pixels × horizontal M pixels (M is an integer of 1 or more) (k = (M × M)). For example, one block BL is an area including sub-block SBs of L vertical × L horizontal (L is an integer of 2 or more) in this embodiment. That is, each block BL of this embodiment is a region of vertical (L × M) pixels × horizontal (L × M) pixels. In this embodiment, since M = 5 and L = 5, each block BL is an area of 25 vertical pixels × 25 horizontal pixels (N = 625).

In S410, the CPU 210 generates partial image data indicating an image in the block of interest and histogram data indicating the distribution of values of a plurality of pixels in the block of interest among the scan data (RGB image data). Histogram data is generated by classifying each of the three component values of R, G, and B per pixel into a plurality of classes according to the component values. In this embodiment, histogram data is generated with each of the 256 gradation values that can be taken by the values of the R, G, and B components as one class. As a result, it is possible to accurately determine whether or not the block BL is a character block even for a color image in which the characters are expressed in chromatic colors.

FIG. 14 is a diagram showing an example of the histogram shown by the histogram data. The histogram HGa in FIG. 14 (A) is a histogram of the block BLa located at the edge portion of the character Ob7 (FIG. 3 (A)). The histogram HGb in FIG. 14 (B) is a histogram of the block BLb located at the edge portion in the photograph Ob3 (FIG. 3 (A)).

In S413, the CPU 210 uses the generated histogram data to calculate the standard deviation σ of the values of the plurality of pixels in the block of interest. The standard deviation σ is calculated using the following equation (1).

ここで、Ｖｉは、注目ブロック内の（３×Ｎ）個の成分値である。成分値の個数は、Ｎ個の画素のそれぞれが、３個の成分値を含むために、合計で（３×Ｎ）個である。Ｖａｖｅは、注目ブロック内の（３×Ｎ）個の成分値の平均値である。標準偏差σは、注目ブロック内の画素の値のばらつきの程度を示す指標値であり、標準偏差σが大きいほど、注目ブロック内の画素の値のばらつきが大きい。

Here, Vi is (3 × N) component values in the block of interest. The number of component values is (3 × N) in total because each of the N pixels includes three component values. Wave is the average value of (3 × N) component values in the block of interest. The standard deviation σ is an index value indicating the degree of variation in the values of the pixels in the block of interest, and the larger the standard deviation σ is, the greater the variation in the values of the pixels in the block of interest.

Here, in order to make the characters easier to read, in general, the color of the characters and the color of the background of the characters are often significantly different in brightness. For example, when the color of the characters is relatively dark (for example, black), the background color of the characters is likely to be relatively light (for example, white). Further, when the color of the character is made relatively light, the background color of the character is likely to be made relatively dark. Further, at the edge portion of the character, since the edge strength is relatively high, the pixel value changes abruptly. For this reason, even when a small block of about 25 pixels vertically × 25 pixels horizontally is set, the histogram HGa of the block BLa located at the edge portion of the character has two peaks at relatively distant positions. Va and Vb appear (FIG. 14 (A)). As a result, the standard deviation σt (FIG. 14 (A)) of the block BLa located at the edge portion of the character becomes relatively large.

On the other hand, the brightness and the like of the edges in the photograph (for example, halftone dots in the photograph and the edges of objects) are not always significantly different on both sides of the edges. Further, at the edge in the photograph, the edge strength is generally lower than that of the character, so that the pixel value changes gently. Therefore, when a small block of about 25 pixels vertically × 25 pixels horizontally is set, the distribution range of the pixel values included in the block BLb located at the edge portion in the photograph becomes relatively narrow. For this reason, two peaks Vb and Vd appear at relatively close positions in the histogram HGb of the block BLb located at the edge portion in the photograph. As a result, the standard deviation σp (FIG. 14 (B)) of the block BLb located at the edge portion in the photograph becomes relatively small.

Utilizing such a tendency of the standard deviation σ, the CPU 210 uses a character block indicating a character and a non-character block indicating no character based on the standard deviation σ, as shown in S415 to S430 described later. , Determine whether it is an unknown block that indicates a character or is unknown. When the standard deviation σ is TH1 ≦ σ, the CPU 210 determines that the block of interest is a character block. When the standard deviation σ is TH2 ≦ σ <TH1, the CPU 210 determines that the block of interest is an unknown block. When the standard deviation σ is σ <TH2, the CPU 210 determines that the block of interest is a non-character block. The threshold values TH1 and TH2 are empirically predetermined by analyzing image data including a plurality of characters and photographs, for example.

Here, when the character has a relatively large size, the attention block can be set not only at the edge of the character but also inside the character. In this case, the standard deviation σ is a small value because the characters are generally monochromatic. Therefore, in this case, the attention block including the pixels constituting the character is determined to be a non-character block. However, in this embodiment, character pixels are sharpened to sharpen the edges of characters, and non-character pixels are smoothed to smooth non-character images such as photographs. Be transformed. Therefore, the block including the pixels of the edge portion of the character may be determined to be a character block with high accuracy, and the block containing only the pixels inside the character may be determined to be a non-character block.

When the entire small character is included in one block of interest, the entire small character is specified as a character pixel without distinguishing between the edge and the inside. In this case, since both the character pixels and the pixels constituting the background of the characters are included in the attention block, the standard deviation σ of the attention block is relatively large. In this case, the attention block including the entire character is accurately determined as the character block.

Further, the attention block may be set not at the edge in the photograph but at the edge portion between the outer edge of the photograph and the outer portion of the photograph (for example, the block BLx in FIG. 14B). In this case, at the edge between the outer edge of the photograph and the outer portion of the photograph, the brightness and the like may be significantly different on both sides of the edge. Further, at the edge, the edge strength may be relatively high. Therefore, in this case, the block of interest including the outer edge of the photograph is determined to be the character block. However, even if the edge portion of the outer edge of the photograph is sharpened to emphasize the outer edge of the photograph, there is no problem in image quality. For this reason, a block containing an edge (for example, a halftone dot or an object edge) in a photo that has a problem in image quality when the edge is emphasized may be accurately determined to be a non-character block, and the photo A block including an outer edge may be determined as a character block.

FIG. 15 is a diagram showing an example of determination for each block BL. For example, when the block BL (1) of FIG. 15 (A) and the block BL (2) of FIG. 15 (B) are attention blocks, the characters occupy a relatively wide range in the attention block, so that the characters occupy a relatively wide range. The attention block is determined to be a character block. For example, when the block BL (3) of FIG. 15 (C) is the attention block, the character is included in the attention block, but the range occupied by the character is relatively narrow, so that the attention block is an unknown block. Is judged to be. For example, when the block BL (4) of FIG. 15 (D) is the attention block, the attention block is determined to be a non-character block because no character is included in the attention block. Hereinafter, the processes of S415 to S430 will be specifically described.

In S415, the CPU 210 determines whether or not the standard deviation σ calculated in S410 is equal to or greater than the threshold TH1. When the standard deviation σ is equal to or greater than the threshold value TH1 (S415: YES), it is determined that the block of interest is a character block. Therefore, in this case, in S420, the CPU 210 sets the values of all the pixels in the block of interest to the values indicating the characters. If the standard deviation σ is less than the threshold TH1 (S415: NO), S420 is skipped.

FIG. 16 is a diagram showing an example of setting a pixel value in the block determination data. 16 (A) to 16 (D) conceptually show the block determination image BI represented by the block determination data. When the block BL (1) of FIG. 15 (A) and the block BL (2) of FIG. 15 (B) are attention blocks, it is determined that the attention block is a character block. Also, as shown in FIGS. 16A and 16B, the values of all the pixels in the blocks BL (1) and BL (2) are set to the value "1" indicating the character.

In S425, the CPU 210 determines whether the standard deviation σ is less than the threshold TH2. If the standard deviation σ is less than the threshold TH2 (S425: YES), the block of interest is determined to be a non-character block. Therefore, in this case, in S430, the CPU 210 sets the values of all the pixels in the block of interest to the values indicating non-characters. If the standard deviation σ is greater than or equal to the threshold TH2 (S425: NO), S430 is skipped.

When the block BL (4) of FIG. 15 (D) is the block of interest, it is determined that the block of interest is a non-character block. Therefore, also in the block determination image BI, as shown in FIG. 16 (D). , The values of all the pixels in the block BL (4) are set to the value "2" indicating non-characters.

If the standard deviation σ is equal to or greater than the threshold value TH2 and less than the threshold value TH1 (S415: NO and S425: NO), the block of interest is determined to be an unknown block. Therefore, in this case, the values of all the pixels in the block of interest are not changed. That is, at this point, the pixel having the value "1" indicating the character is maintained as the value indicating the character, and the pixel having the value "2" indicating the non-character is maintained as the value indicating the non-character. Pixels having a value "0" indicating unknown are maintained at the value indicating unknown.

When the block BL (3) of FIG. 15 (C) is the block of interest, it is determined that the block of interest is an unknown block. Therefore, in the block determination image BI, as shown in FIG. 16 (C), the block is blocked. The values of all the pixels in BL (4) are maintained unchanged.

In S435, the CPU 210 moves the block of interest by M pixels to the right. That is, the attention block is moved to the right by one subblock SB. For example, when the block BL (1) in FIG. 13 is a block of interest, the block BL (2) is set as a new block of interest. When the block BL (q-1) of FIG. 13 is the block of interest, the block BL (q) is set as a new block of interest.

In S440, the CPU 210 determines whether or not the right end of the attention block has moved to the right side of the right end of the scan image SI as a result of moving the attention block by M pixels to the right. That is, it is determined whether or not the new attention block after the movement protrudes to the right side of the scanned image SI. For example, when the new attention block is the block BL (q) or the block BL (e) of FIG. 13, it is determined that the right end of the attention block has moved to the right side of the right end of the scanned image SI.

When the right end of the attention block has not moved to the right side of the right end of the scanned image SI (S440: NO), the CPU 210 returns to S410. In this way, for example, while shifting the attention block by M pixels to the right, the determination for each block (S410 to S430) is sequentially performed. In the example of FIG. 13, it is determined whether each block BL is a character block, a non-character block, or an unknown block in the order of blocks BL (1), BL (2), and BL (3).

When the right end of the attention block is moved to the right side of the right end of the scan image SI (S440: YES), in S445, the CPU 210 moves the attention block to the left end of the scan image SI, and in S450, attention is paid. The block is moved downward by M pixels.

In S455, the CPU 210 determines whether or not the lower end of the attention block has moved below the lower end of the scanned image SI as a result of moving the attention block downward by M pixels. That is, it is determined whether or not the new attention block after the movement protrudes below the scanned image SI. For example, when the new attention block is the block BL (e + 1) of FIG. 13, it is determined that the lower end of the attention block has moved below the lower end of the scanned image SI. For example, when the new attention block after movement is the block BL (e + 1) of FIG. 13, it is determined that the lower end of the attention block has moved below the lower end of the scanned image SI.

If the lower end of the attention block has not moved below the lower end of the scanned image SI (S455: NO), the CPU 210 returns to S410. In this way, for example, while shifting the block of interest downward by M pixels, the block BL for one line from the left end to the right end is sequentially determined line by line. For example, next to the rightmost block BL (q-1) in FIG. 13, the block of interest to be determined is the leftmost block BL (q + 1) in the lower row by M pixels.

When the lower end of the block of interest moves below the lower end of the scanned image SI (S455: YES), the determination of all the blocks BL is completed, so the CPU 210 proceeds to S460.

In S460, the CPU 210 determines whether or not a value “0” indicating unknown remains in the block determination data. If a value indicating unknown remains, in S465, the CPU 210 sets the value indicating unknown to the value "1" indicating a character. As a result, the value of each pixel of the block determination data becomes either a value "1" indicating a character or a value "2" indicating a non-character.

In S470, the CPU 210 changes the non-character value "2" to "0" and converts the block determination data into binary data having either a value of "1" or "0". As a result, the value "1" indicating that the character is a value, that is, the second character candidate pixel described above, and the value indicating a non-character, that is, the value indicating that the character is not the second character candidate pixel described above, " Block determination data having any of the values "0" and "0" for each pixel is generated.

In the character identification process of the present embodiment described above (S20 in FIG. 2), in S22 to S26 of FIG. 2, the CPU 210 determines for each pixel whether or not it is an edge pixel constituting an edge in the scanned image SI. By judging, a plurality of first candidate pixels are determined. In S28 of FIG. 2, the CPU 210 determines, for each block, whether or not each of the plurality of blocks BL arranged on the scanned image SI is a character block indicating a character, thereby performing a plurality of first blocks. 2 character candidate pixels are determined. In the judgment for each block, the CPU 210 generates histogram data showing the distribution of a plurality of pixels in the block BL for each block BL (S410 in FIG. 12), and uses the histogram data to generate the plurality of block BLs. It is determined whether or not each of the above is a character block (S413 to S430 in FIG. 12). In S29 of FIG. 2, the CPU 210 determines that the pixel is determined to be the first character candidate pixel and is determined to be the second character candidate pixel among the plurality of pixels in the scanned image SI. , Specified as a character pixel. As a result, for example, even if the pixels constituting the halftone dots (for example, the halftone dots in the photograph) are erroneously determined to be the first character candidate pixels by the judgment for each pixel, the judgment for each block When the pixel constituting the halftone dot is not determined to be the second character candidate pixel, the pixel constituting the halftone dot is not erroneously specified as the character pixel. By using the histogram data for the determination for each block BL, the second character candidate pixel can be determined without requiring complicated processing. Therefore, for example, even if the scanned image SI is an image including halftone dots, the character pixels in the scanned image SI can be accurately identified.

FIG. 17 is a diagram illustrating the effect of the embodiment. 17 (A) to 17 (D) show a scan image SI indicated by scan data, an edge identification image EI indicated by edge identification data, a block determination image BI indicated by block determination data, and characters indicated by character identification data. Each specific image TI is conceptually shown. The squares shown by the broken lines in these images SI, EI, BI, and TI each indicate the pixel Px.

Like the scanned image SI shown in FIG. 17A, the scanned image SI may include the characters Tx as well as halftone dot DTs that form objects other than the characters (for example, a photograph). This is because, as described above, the scan data is the data generated by reading the printed matter. In the process of specifying the edge pixels (first character candidate pixels) of S22 to S26 of this embodiment, as described above, various halftone dots are used to prevent the halftone dots from being erroneously specified as the first character candidate pixels. However, if emphasis is placed on suppressing the omission of identification of the first character candidate pixel indicating the edge of the character, it is sufficient that the halftone dot is erroneously specified as the first character candidate pixel. It is difficult to suppress it. For this purpose, for example, as shown in the edge specific image EI of FIG. 17B, not only the edge pixel Egt corresponding to the character Tx but also the edge pixel Egd corresponding to the halftone dot DT is the first in the edge specific data. Can be identified as a character candidate pixel of.

In the block determination process of S28 of this embodiment, for each block BL, determination including whether or not it is a character block is performed according to the positions of N pixels in the block and the values of N pixels. Although the spatial resolution is coarser than the judgment for each pixel, the judgment error is relatively small. More specifically, in this embodiment, the block BL containing characters and the block BL containing non-characters (particularly photographs) have different pixel value distribution characteristics (FIG. 13). Using the histogram data showing the distribution of the pixels in the block BL, it is determined whether or not the block BL is a character block. For this reason, for example, in the block determination image BI of FIG. 17C, for example, although roughly, the pixels in the region containing the character Tx are specified as the second character candidate pixels and include the halftone dot DT. Pixels in the region are not specified as second character candidate pixels.

As a result, if the character identification data is generated by taking the logical product of the edge identification data and the block determination data, the pixel indicating the character Tx can be converted into a character pixel as shown in the character identification image TI of FIG. 17 (D). And the pixel indicating the halftone dot DT can be appropriately specified as a non-character pixel.

As a result, for example, in order to remove a pixel erroneously specified as a character pixel even though the halftone dot DT is indicated, a noise removal process for removing an isolated character pixel is executed for the character identification data. You don't even have to. When such noise removal processing is executed, not only character pixels indicating halftone dot DT but also character pixels that tend to be isolated, such as periods, commas, and voiced sound, may be removed. Character pixels indicating periods, commas, voiced sounds, etc. should not be removed, so if they are removed by mistake, inconveniences such as blurring of part of the characters may occur and the image quality of the output image may deteriorate. ..

Further, in the above embodiment, the CPU 210 determines whether or not the standard deviation σ calculated using the histogram data is TH1 or more (S415 in FIG. 12), and when the standard deviation σ is TH1 or more (S45 in FIG. 12). YES in S415 of FIG. 12), it is determined that the block of interest is a character block (S420 of FIG. 12), and when the standard deviation σ is less than TH1 (NO in S415 of FIG. 12), attention is paid. The block is determined to be a non-character block or an unknown block (S425, S430 in FIG. 12). In other words, the CPU 210 uses the histogram data to determine whether or not the variation in the values of the plurality of pixels in the block of interest is equal to or greater than the reference, and the variation in the values of the plurality of pixels in the block of interest is. When it is equal to or more than the reference, it is determined that the attention block is a character block, and when the variation in the values of a plurality of pixels in the attention block is less than the reference, it is determined that the attention block is not a character block. As a result, it is possible to accurately determine whether or not the block BL is a character block based on the variation in the values of the plurality of pixels in the block BL.

Further, in the above embodiment, each of the values of the plurality of pixels of the scan data is an RGB value including the plurality of component values, and the generated histogram data is the value of each of the plurality of component values. It is the data obtained by classifying according to (FIG. 13). As a result, for example, even for color image data in which characters are represented by chromatic colors (RGB image data in this embodiment), it is possible to accurately determine whether or not the block BL in the image is a character.

Further, according to the above embodiment, for example, as shown in FIGS. 15 and 16, the block BL (1), the block BL (2), the block BL (3), and the block BL (4) are partially connected to each other. overlapping. The CPU 210 overlaps each other as to whether or not n pixels (n is an integer satisfying 0 <n <N) in the overlapping region of these blocks are pixels indicating characters (second character candidate pixels). The decision is made based on at least one of the judgment results of a plurality of blocks. As a result, block determination data indicating whether or not the second character candidate pixel is used can be generated in units of sub-block SB smaller than each block BL.

For example, in this embodiment, as shown in S420 and S430, when it is determined that the attention block is a character block or a non-character block, in the block determination data, the values of all the pixels in the attention block are the determination results. It is set according to. That is, it is assumed that both the first block and the second block are determined to be blocks other than the unknown block (that is, a character block or a non-character block). In this case, with respect to the overlapping area of the first block and the second block, the judgment result of the block whose judgment processing order is later than that of the first block and the second block has priority ( 16 (A)-(D)).

Further, in this embodiment, as described above, when it is determined that the attention block is an unknown block, the values of all the pixels in the attention block are not changed. That is, it is assumed that one of the first block and the second block is determined to be an unknown block, and the other is determined to be either a character block or a non-character block. In this case, regarding the overlapping area of the first block and the second block, the block determined to be either a character block or a non-character block among the first block and the second block. (See FIGS. 16B to 16D). In other words, if the first block is determined to be an unknown block and the second block is determined to be a character block, the pixels in the overlapping area are pixels indicating characters (second). Character candidate pixel). When the first block is determined to be an unknown block and the second block is determined to be a non-character block, the pixels in the overlapping area are pixels indicating non-characters (second character). It is determined that the pixel is not a candidate pixel). Further, when it is determined that the first block is a character block and the second block is an unknown block, the pixels in the overlapping region are determined to be characters indicating characters. To. When the first block is determined to be a non-character block and the second block is determined to be an unknown block, the pixels in the overlapping region are determined to be non-character pixels. To. As a result, by determining whether it is a character block, a non-character block, or an unknown block for each block, whether or not the pixel in the overlapping area is a pixel indicating a character (second character candidate pixel). Can be determined appropriately.

B. Modification example:

(1) In the block determination process of FIG. 12 of the above embodiment, it is determined whether or not the block of interest is a character block by using the standard deviation σ. Instead of this, for example, another determination method may be used to determine whether or not the block of interest is a character block. For example, even if it is determined whether or not the attention block is a character block by using an index value indicating the variation of a plurality of pixels in the attention block and different from the standard deviation σ. good. The index value indicating the variation of a plurality of pixels in the block of interest is, for example, a peak corresponding to the smallest component value and a peak corresponding to the largest component value among the plurality of peaks in the histogram. It may be the distance between them.

Further, the CPU 210 is a feature derived by using the histogram data of the block BL, and uses a feature different from the variation of a plurality of pixels in the block BL to determine whether or not the block of interest is a character block. You may judge whether. For example, in the block BL showing characters, a relatively thin and high peak corresponding to the background and a relatively thin and high peak corresponding to the character appear in the histogram. Therefore, the CPU 210 may determine that the attention block is a character block when two peaks that are thinner than the reference and higher than the reference are detected in the histogram of the attention block.

(2) In the block determination process of the above embodiment, it is determined whether or not the block is a character block while shifting the attention block of vertical (L × M) pixels × horizontal (L × M) pixels by M pixels. A plurality of blocks arranged on the scanned image SI overlap each other (FIG. 13). Instead of this, a plurality of blocks may be arranged on the scanned image SI so that the plurality of blocks do not overlap each other.

(3) In the block determination process of the above embodiment, the CPU 210 determines whether the block of interest is a character block, a non-character block, or an unknown block. Instead, the CPU 210 may determine whether the block of interest is a character block or a non-character block. In this case, for example, the threshold value TH1 used in S415 and the threshold value TH2 used in S425 may be set to the same value. For example, TH1 = TH2 = 50% may be set.

(4) In the image processing of FIG. 2 of the above embodiment, the second binary image data generation processing of S24 and the composition processing of S26 may be omitted. That is, the plurality of edge pixels specified in the first binary image data generation process may be the final edge identification data.

(5) In the above embodiment, as described above, as shown in S420 and S430 of FIG. 12, when the attention block is determined to be a character block or a non-character block, in the block determination data, the attention block is contained. The values of all the pixels are set according to the judgment result. Instead of this, in the block determination data, of the N pixels in the block of interest, only the value of the pixel having a value indicating unknown may be set according to the determination result. That is, it is determined that both the first block and the second block that overlap each other are blocks other than the unknown block (that is, a character block or a non-character block). In this case, regarding the overlapping area of the first block and the second block, even if the judgment result of the block whose judgment processing order is earlier than that of the first block and the second block is prioritized. good.

(6) In the block determination process of FIG. 12 of the above embodiment, if a value indicating unknown remains in the block determination data after the determination for all the block BLs (S460: YES), the CPU 210 determines. In S465, the value indicating unknown is set to the value indicating characters. This is to prevent a part of the character pixel from being mistakenly identified as a non-character pixel and to avoid inconvenience such as a part of the character being blurred. For example, when it is important to prevent a part of non-character pixels from being mistakenly identified as a character pixel and to avoid inconveniences such as conspicuous halftone dots, the CPU 210 makes an unknown question in S465. The indicated value may be set to a value indicating a non-character.

(7) In the first binary image data generation process (FIG. 5) of FIG. 5, luminance image data is used as the single component image data (S120). Instead of this, the average component value image data in which the average value of the three component values (R value, G value, B value) included in the RGB values of the corresponding pixels of the scan data is used as the value of each pixel is used. May be done.

(8) In the second binary image data generation process (FIG. 9) of the above embodiment, the minimum component data is used as the single component image data (S300). Instead of this, the maximum component data or the inverted minimum component data may be used.

The maximum component data includes a plurality of values corresponding to a plurality of pixels included in the scan data, and each of the plurality of values is the maximum component value Vmax of the corresponding pixel of the scan data. The maximum component value Vmax is the maximum value among a plurality of component values (R value, G value, B value) included in the RGB values of the corresponding pixels of the scan data.

The inversion minimum component data is acquired as follows. First, for each of the values (RGB values) of the plurality of pixels included in the scan data, the inverted color values in which the plurality of component values (R value, G value, B value) are inverted are generated. Assuming that the RGB values before inversion are (Rin, Gin, Bin), the inverted RGB values (Rout, Gout, Bout) are represented by the following equations (1) to (3).

Rout = Rmax-Rin ... (1)
Gout = Gmax-Gin ... (2)
Bout = Bmax-Bin ... (3)

Here, Rmax, Gmax, and Bmax are the maximum values that the R value, G value, and B value can take, respectively, and in this embodiment, Rmax = Gmax = Bmax = 255. Image data in which these inverted RGB values are the values of a plurality of pixels is generated as inverted image data. Then, the inverted minimum component data is generated using the inverted image data. Specifically, the inverted minimum component value VRmin is acquired from each of the plurality of inverted RGB values included in the inverted image data. The inverted minimum component value VRmin is the minimum value among a plurality of component values (R value, G value, B value) included in the inverted RGB value. The inversion minimum component data is image data in which these inversion minimum component values VRmin are values of a plurality of pixels.

The inverted minimum component value VRmin is an inverted value of the maximum component value, and the relationship of VRmin = (255-Vmax) is established. Therefore, both the maximum component data and the inverted minimum component data are values based on the maximum value among the plurality of component values included in the value of each pixel of the scan data (the inverted value of the maximum value, or the inverted value of the maximum value, or It can be said that the maximum value itself) is the image data in which the pixel value is used.

As shown in FIG. 10, the maximum component values Vmax of C, M, Y, K, and W are 255, 255, 255, 0, and 255, which are the same values except for black (K). Therefore, in the maximum component data and the inverted minimum component data, among the five types of elements constituting the halftone dot region, that is, the dots of C, M, Y, and K, and the background color (white) of the paper. The difference between the values indicating the four types of elements (dots C, M, Y and the background color (white) of the paper) is suppressed. As a result, when the maximum component data or the inverted minimum component data is used, it is possible to suppress the identification of edge pixels due to halftone dots, as in the case of using the minimum component data.

(9) In each of the above embodiments, character sharpening processing is executed for character pixels (S40 in FIG. 2), and halftone dot smoothing processing is executed for non-character pixels (S30 in FIG. 2). ). Instead of this, antialiasing processing for improving the appearance of the character may be executed on the character pixel. Further, for non-character pixels, for example, in order to reduce the amount of color material used during printing, a process of skipping colors (a process of converting to white) may be executed. In general, it is preferable that character pixels and non-character pixels are subjected to different image processing. Alternatively, the specific image processing may be executed on either the character pixel or the non-character pixel, and the specific image processing may not be executed on the other.

(10) In the above embodiment, a Sobel filter is used in the edge extraction process of S130 of FIG. 5 and S320 of FIG. Instead of this, in these edge extraction processes, other edge extraction filters such as a Roberts filter and a Laplacian filter may be used.

(11) In the above embodiment, the target image data is scan data, but is not limited to this. The target image data may be generated by reading the printed matter with a digital camera equipped with a two-dimensional image sensor.

(12) In the above embodiment, edge specific data is generated by ORing the first binary image data and the second binary image data (S26 in FIG. 2). Instead of this, edge specific data may be generated by ORing the first binary image data, the second binary image data, and the third binary image data. As the third binary image data, for example, the binary image data generated by using the above-mentioned maximum component data may be used. As a result, it is possible to further suppress the omission of specific edges such as characters.

(13) The first binary image data generation process (FIG. 5) and the second binary image data generation process (FIG. 9) of the above embodiment can be appropriately changed. For example, all or part of the processing of S110, S110, and S140 in FIG. 5 can be omitted. Further, all or a part of S310 and S330 in FIG. 9 can be omitted.

(14) The image processing device that realizes the image processing of FIG. 2 is not limited to the multifunction device 200, and may be various devices. For example, the scanner or the digital camera may execute the image processing of FIG. 2 in order to generate print data to be supplied to the printer by using the image data generated by the scanner or the digital camera. Further, for example, a connected terminal device (for example, terminal device 100) or a server (not shown) capable of communicating with the scanner or printer executes the image processing of FIG. 2 using the scan data acquired from the scanner. , Print data may be generated and the print data may be supplied to the printer. Further, a plurality of computers (for example, a cloud server) capable of communicating with each other via a network may partially share the functions required for image processing and execute image processing as a whole. In this case, the entire plurality of computers is an example of an image processing device.

(15) In each of the above embodiments, a part of the configuration realized by the hardware may be replaced with software, and conversely, a part or all of the configuration realized by the software may be replaced with the hardware. You may do so. For example, the process of generating the histogram data of S410 and S420 of FIG. 12 and calculating the standard deviation σ using the histogram data may be executed by dedicated hardware such as ASIC.

Although the present invention has been described above based on Examples and Modifications, the above-described embodiments of the invention are for facilitating the understanding of the present invention and do not limit the present invention. The present invention may be modified or improved without departing from the spirit and claims, and the present invention includes an equivalent thereof.

100 ... Terminal device, 200 ... Complex machine, 210 ... CPU, 220 ... Volatile storage device, 230 ... Non-volatile storage device, 240 ... Display unit, 250 ... Operation unit, 270 ... Communication IF, 280 ... Print execution unit, 290 ... Reading execution unit, PG ... Computer program, SI ... Scanned image, TI ... Character specific image, GI ... Smoothed image, FI ... Processed image, EI ... Edge specific image, BI ... Block judgment image, YI ... Brightness image, SI ... scan image, BL ... block, DT ... halftone dot, SB ... subblock, HGa, HGb ... histogram

Claims (9)

It is an image processing device
An image acquisition unit that acquires target image data indicating a target image, and the target image data is generated by reading a printed matter using an image sensor.
A character identification unit that identifies a character pixel indicating a character from a plurality of pixels in the target image,
With
The character identification part is
By using the target image data to determine for each pixel whether or not each of the plurality of pixels in the target image is an edge pixel constituting an edge in the target image, the edge pixel is obtained. A plurality of first candidate pixels judged to be determined are determined, and
Using the target image data, histogram data showing the distribution of the plurality of pixels in the block is generated for each of the plurality of blocks arranged on the target image.
By using the histogram data to determine for each block whether or not each of the plurality of blocks is a character block indicating a character, a plurality of blocks in the block determined to be the character block. Determine the second candidate pixel,
Image processing that identifies the pixel determined to be the first candidate pixel and the pixel determined to be the second candidate pixel among the plurality of pixels in the target image as the character pixel. apparatus. The image processing apparatus according to claim 1.
The character identification part is
Using the histogram data, it is determined whether or not the variation in the values of the plurality of pixels in the block is equal to or greater than the reference value.
When the variation in the values of the plurality of pixels in the block is equal to or greater than the reference, it is determined that the block is a character block, and the block is determined to be a character block.
An image processing device that determines that the block is not a character block when the variation in the values of the plurality of pixels in the block is less than the reference. The image processing apparatus according to claim 1 or 2.
Each of the values of the plurality of pixels is a color value including a plurality of component values.
The histogram data is an image processing apparatus which is data obtained by classifying each of the plurality of component values according to the values. The image processing apparatus according to any one of claims 1 to 3.
The character identification part is
Using the target image data, it is the first image data including a plurality of first values corresponding to the plurality of pixels included in the target image data, and is the first image data including the plurality of first values. Each generates the first image data, which is a brightness value based on the value of the corresponding pixel.
A plurality of first edge pixels indicating edges in the first image represented by the first image data are identified.
Using the target image data, it is the second image data including a plurality of second values corresponding to the plurality of pixels included in the target image data, and is the second image data of the plurality of second values. Each generates the second image data, which is a value based on the minimum component value or the maximum component value among the plurality of component values of the corresponding pixels.
A plurality of second edge pixels indicating the edges in the second image indicated by the second image data are identified.
Among the plurality of pixels in the target image, the plurality of pixels corresponding to the plurality of first edge pixels and the plurality of pixels corresponding to the plurality of second edge pixels are included. The pixel group is a plurality of the first candidate pixels that do not include a plurality of pixels that do not correspond to the plurality of first edge pixels and the plurality of second edge pixels. An image processing device that determines that. The image processing apparatus according to any one of claims 1 to 4.
The plurality of blocks include a first block and a second block that partially overlaps the first block.
The character identification part is
The first block is determined whether or not the character block,
Before Stories second block is judged whether or not the character block,
Whether or not the n pixels (n is an integer of 1 or more) in the overlapping region where the first block and the second block overlap are the second candidate pixels is determined for the first block. An image processing device that determines based on at least one of the determination result of the above and the determination result of the second block. The image processing apparatus according to claim 5.
The character identification part is
Using the histogram data, it is determined for each block whether the block of interest is the character block, the non-character block that does not show characters, or the unknown block that shows characters or is unknown.
When the first block is determined to be the unknown block and the second block is determined to be the character block, the n pixels in the overlapping region are the second. Determined to be a candidate pixel for
When it is determined that the first block is the unknown block and the second block is determined to be the non-character block, the n pixels in the overlapping region are the first. Determined that it is not a candidate pixel of 2,
When the first block is determined to be the character block and the second block is determined to be the unknown block, the n pixels in the overlapping region are the second. Determined to be a candidate pixel for
When it is determined that the first block is the non-character block and the second block is determined to be the unknown block, the n pixels in the overlapping region are the first. An image processing device that determines that it is not a candidate pixel of 2. The image processing apparatus according to any one of claims 1 to 6, further comprising.
Of the target image data, the first image processing is executed on the identified value of the character pixel, and the value of the pixel different from the character pixel is different from the first image processing. An image processing apparatus including an image processing unit that executes the image processing of the above and generates the target image data that has been image-processed. The image processing apparatus according to claim 7, further
An image processing apparatus including a print data generation unit that generates print data using the target image data that has been image-processed. It ’s a computer program,
An image acquisition function for acquiring target image data indicating a target image, wherein the target image data is generated by reading a printed matter using an image sensor, and the image acquisition function.
A character identification function that identifies a character pixel indicating a character from a plurality of pixels in the target image, and
To the computer,
The character identification function is
By using the target image data to determine for each pixel whether or not each of the plurality of pixels in the target image is an edge pixel constituting an edge in the target image, the edge pixel is obtained. A plurality of first candidate pixels judged to be determined are determined, and
Using the target image data, histogram data showing the distribution of the plurality of pixels in the block is generated for each of the plurality of blocks arranged on the target image.
By using the histogram data to determine for each block whether or not each of the plurality of blocks is a character block indicating a character, a plurality of blocks in the block determined to be the character block. Determine the second candidate pixel,
A computer program that identifies a pixel determined to be the first candidate pixel and a pixel determined to be the second candidate pixel among a plurality of pixels in the target image as the character pixel. ..

Images